© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10580
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or references with brackets

    np_acts-logits-general · gemini-2.0-flash

    ActionLink("Update"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Florida
    -0.35
     networking
    -0.34
    o
    -0.34
    sub
    -0.33
     우
    -0.33
     Networking
    -0.33
     타
    -0.32
    coefficient
    -0.32
     la
    -0.32
    str
    -0.32
    POSITIVE LOGITS
    AndEndTag
    1.05
     ModelExpression
    0.81
    aarrggbb
    0.81
    WriteLiteral
    0.77
     HttpNotFound
    0.75
     indígen
    0.71
    ftagPool
    0.68
     pleaſure
    0.67
    cshtml
    0.66
     IActionResult
    0.65
    Activations Density 0.277%

    No Known Activations